
import pandas as pd

df = pd.read_csv('Reviews.csv')
df.head()


import matplotlib.pyplot as plt
import seaborn as sns
color = sns.color_palette()
%matplotlib inline
import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls
import plotly.express as px


# Reviewing the product scores to see if customer ratings are positive or negative
fig = px.histogram(df, x="Score")
fig.update_traces(marker_color="purple", marker_line_color='rgb(8,48,107)', marker_line_width=1.5)
fig.update_layout(title_text='Product Score')
fig.show()


# assign reviews with score > 3 as positive sentiment
# score < 3 negative sentiment
# remove score = 3
df = df[df['Score'] != 3]
df['sentiment'] = df['Score'].apply(lambda rating : +1 if rating > 3 else -1)


# split the data frame into positive and negative

positive = df[df['sentiment'] == 1]
negative = df[df['sentiment'] == -1]


# distribution of reviews conclude that reviews are mostly positive 

df['sentimentt'] = df['sentiment'].replace({-1 : 'negative'})
df['sentimentt'] = df['sentimentt'].replace({1 : 'positive'})
fig = px.histogram(df, x="sentimentt")
fig.update_traces(marker_color="indianred",marker_line_color='rgb(8,48,107)',
                  marker_line_width=1.5)
fig.update_layout(title_text='Product Sentiment')
fig.show()


# clean the data of punctuation

def remove_punctuation(text):
    final = "".join(u for u in text if u not in ("?", ".", ";", ":",  "!",'"'))
    return final
df['Text'] = df['Text'].apply(remove_punctuation)
df = df.dropna(subset=['Summary'])
df['Summary'] = df['Summary'].apply(remove_punctuation)


dfNew = df[['Summary','sentiment']]
dfNew.head()


import numpy as np
# random split train and test data
index = df.index
df['random_number'] = np.random.randn(len(index))
train = df[df['random_number'] <= 0.8]
test = df[df['random_number'] > 0.8]


# count vectorizer:
from sklearn.feature_extraction.text import CountVectorizer

# Convert a collection of text documents to a matrix of token counts

# all possible words in matrix
vectorizer = CountVectorizer(token_pattern=r'\b\w+\b')
train_matrix = vectorizer.fit_transform(train['Summary'])
test_matrix = vectorizer.transform(test['Summary'])


# Logistic Regression
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression()


X_train = train_matrix
X_test = test_matrix
y_train = train['sentiment']
y_test = test['sentiment']


lr.fit(X_train,y_train)

C:\Users\Jonic\anaconda3\envs\GPU\lib\site-packages\sklearn\linear_model\_logistic.py:765: ConvergenceWarning:

lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression

LogisticRegression()


predictions = lr.predict(X_test)


# find accuracy, precision, recall:
from sklearn.metrics import confusion_matrix,classification_report
new = np.asarray(y_test)
confusion_matrix(predictions,y_test)

#              predict no       predict yes
#             _______________________________
# actual No  | true negative   false positive
#            |
# actual yes | false negative  true positive

array([[11467,  2285],
       [ 5934, 91845]], dtype=int64)


print(classification_report(predictions,y_test))

# -1 negative reviews
# 1 positive reviews

# precision: tp / (tp + fp)
# recall: tp / (tp + fn) 
# f1-score: 2 * (precision * recall) / (precision + recall)
# support: The support is the number of occurrences of each class in y_true

# macro: Calculate metrics for each label, and find their unweighted mean. 
#  This does not take label imbalance into account.

# weighted: Calculate metrics for each label, and find their 
#  average weighted by support (the number of true instances for each label). 
#  This alters ‘macro’ to account for label imbalance; it can result in an F-score
#  that is not between precision and recall.

              precision    recall  f1-score   support

          -1       0.66      0.83      0.74     13752
           1       0.98      0.94      0.96     97779

    accuracy                           0.93    111531
   macro avg       0.82      0.89      0.85    111531
weighted avg       0.94      0.93      0.93    111531

	Id	ProductId	UserId	ProfileName	HelpfulnessNumerator	HelpfulnessDenominator	Score	Time	Summary	Text
0	1	B001E4KFG0	A3SGXH7AUHU8GW	delmartian	1	1	5	1303862400	Good Quality Dog Food	I have bought several of the Vitality canned d...
1	2	B00813GRG4	A1D87F6ZCVE5NK	dll pa	0	0	1	1346976000	Not as Advertised	Product arrived labeled as Jumbo Salted Peanut...
2	3	B000LQOCH0	ABXLMWJIXXAIN	Natalia Corres "Natalia Corres"	1	1	4	1219017600	"Delight" says it all	This is a confection that has been around a fe...
3	4	B000UA0QIQ	A395BORC6FGVXV	Karl	3	3	2	1307923200	Cough Medicine	If you are looking for the secret ingredient i...
4	5	B006K2ZZ7K	A1UQRSCLF8GW1T	Michael D. Bigham "M. Wassir"	0	0	5	1350777600	Great taffy	Great taffy at a great price. There was a wid...

	Summary	sentiment
0	Good Quality Dog Food	1
1	Not as Advertised	-1
2	Delight says it all	1
3	Cough Medicine	-1
4	Great taffy	1

Building the Classification Model¶